© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14319
    Prev
    Next
    INDEX
    Explanations

    the word "library" and, to a lesser extent, terms common in software licenses, such as "any" and "option".

    oai_token-act-pair · gemini-2.0-flash

    library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {:.
    -0.65
     la
    -0.62
    -
    -0.56
    ,
    -0.56
    reda
    -0.51
     finally
    -0.50
     d
    -0.50
    img
    -0.50
    ImageButton
    -0.50
    invest
    -0.49
    POSITIVE LOGITS
     feroit
    0.95
     auroit
    0.94
     pouvoit
    0.93
    
    0.93
     avoient
    0.91
     Italij
    0.91
     Monfieur
    0.89
     neutre
    0.87
     romain
    0.85
     wuß
    0.85
    Activations Density 2.182%

    No Known Activations